Made some documentation updates & fixes

--Mostly doc block tweaks
	--Added @DocumentedGATKFeature to some walkers that were undocumented because they were ending up in "uncategorized". Very important for GSA: if a walker is in public or protected, it HAS to be properly tagged-in. If it's not ready for the public, it should be in private.
This commit is contained in:
Geraldine Van der Auwera 2013-03-15 13:26:05 -04:00
parent c813259283
commit 95a9ed853d
10 changed files with 60 additions and 30 deletions

View File

@ -70,10 +70,11 @@ import java.util.Map;
/**
* Total (unfiltered) depth over all samples.
*
* While the sample-level (FORMAT) DP field describes the total depth of reads that passed the Unified Genotyper's
* <p>While the sample-level (FORMAT) DP field describes the total depth of reads that passed the caller's
* internal quality control metrics (like MAPQ > 17, for example), the INFO field DP represents the unfiltered depth
* over all samples. Note though that the DP is affected by downsampling (-dcov), so the max value one can obtain for
* N samples with -dcov D is N * D
* </p>
*/
public class Coverage extends InfoFieldAnnotation implements StandardAnnotation, ActiveRegionBasedAnnotation {

View File

@ -69,10 +69,15 @@ import java.util.*;
/**
* Phred-scaled p-value using Fisher's Exact Test to detect strand bias (the variation
* being seen on only the forward or only the reverse strand) in the reads? More bias is
* indicative of false positive calls. Note that the fisher strand test may not be
* calculated for certain complex indel cases or for multi-allelic sites.
* Phred-scaled p-value using Fisher's Exact Test to detect strand bias
*
* <p>Phred-scaled p-value using Fisher's Exact Test to detect strand bias (the variation
* being seen on only the forward or only the reverse strand) in the reads. More bias is
* indicative of false positive calls.
* </p>
*
* <h3>Caveat</h3>
* <p>The Fisher Strand test may not be calculated for certain complex indel cases or for multi-allelic sites.</p>
*/
public class FisherStrand extends InfoFieldAnnotation implements StandardAnnotation, ActiveRegionBasedAnnotation {
private final static Logger logger = Logger.getLogger(FisherStrand.class);

View File

@ -68,7 +68,7 @@ import java.util.Map;
/**
* GC content of the reference around this site
* GC content of the reference around the given site
*
* <p>The GC content is the number of GC bases relative to the total number of bases (# GC bases / # all bases) around this site on the reference.</p>
*

View File

@ -61,7 +61,7 @@ import java.util.List;
* User: rpoplin
* Date: Nov 27, 2009
*
* A collection of the arguments that are common to both CovariateCounterWalker and TableRecalibrationWalker.
* A collection of the arguments that are used for BQSR. Used to be common to both CovariateCounterWalker and TableRecalibrationWalker.
* This set of arguments will also be passed to the constructor of every Covariate when it is instantiated.
*/
@ -131,14 +131,14 @@ public class RecalibrationArgumentCollection {
public boolean RUN_WITHOUT_DBSNP = false;
/**
* CountCovariates and TableRecalibration accept a --solid_recal_mode <MODE> flag which governs how the recalibrator handles the
* BaseRecalibrator accepts a --solid_recal_mode <MODE> flag which governs how the recalibrator handles the
* reads which have had the reference inserted because of color space inconsistencies.
*/
@Argument(fullName = "solid_recal_mode", shortName = "sMode", required = false, doc = "How should we recalibrate solid bases in which the reference was inserted? Options = DO_NOTHING, SET_Q_ZERO, SET_Q_ZERO_BASE_N, or REMOVE_REF_BIAS")
public RecalUtils.SOLID_RECAL_MODE SOLID_RECAL_MODE = RecalUtils.SOLID_RECAL_MODE.SET_Q_ZERO;
/**
* CountCovariates and TableRecalibration accept a --solid_nocall_strategy <MODE> flag which governs how the recalibrator handles
* BaseRecalibrator accepts a --solid_nocall_strategy <MODE> flag which governs how the recalibrator handles
* no calls in the color space tag. Unfortunately because of the reference inserted bases mentioned above, reads with no calls in
* their color space tag can not be recalibrated.
*/

View File

@ -47,6 +47,7 @@
package org.broadinstitute.sting.gatk.walkers.bqsr;
import org.broadinstitute.sting.commandline.*;
import org.broadinstitute.sting.gatk.CommandLineGATK;
import org.broadinstitute.sting.gatk.contexts.AlignmentContext;
import org.broadinstitute.sting.gatk.contexts.ReferenceContext;
import org.broadinstitute.sting.gatk.filters.*;
@ -55,18 +56,27 @@ import org.broadinstitute.sting.gatk.report.GATKReport;
import org.broadinstitute.sting.gatk.report.GATKReportTable;
import org.broadinstitute.sting.gatk.walkers.*;
import org.broadinstitute.sting.utils.exceptions.ReviewedStingException;
import org.broadinstitute.sting.utils.help.DocumentedGATKFeature;
import org.broadinstitute.sting.utils.help.HelpConstants;
import org.broadinstitute.sting.utils.recalibration.*;
import java.io.*;
/**
* Evaluate the performance of the base recalibration process
*
* <p>This tool aims to evaluate the results of the Base Quality Score Recalibration (BQSR) process.</p>
*
* <h3>Caveat</h3>
* <p>This tool is currently experimental. We do not provide documentation nor support for its operation.</p>
*
*/
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_QC, extraDocs = {CommandLineGATK.class} )
@ReadFilters({MappingQualityZeroFilter.class, MappingQualityUnavailableFilter.class, UnmappedReadFilter.class, NotPrimaryAlignmentFilter.class, DuplicateReadFilter.class, FailsVendorQualityCheckFilter.class})
@PartitionBy(PartitionType.READ)
public class RecalibrationPerformance extends RodWalker<Integer, Integer> implements NanoSchedulable {
@Output(doc="Write output to this file")
@Output
public PrintStream out;
@Input(fullName="recal", shortName="recal", required=false, doc="The input covariates table file")

View File

@ -48,6 +48,7 @@ package org.broadinstitute.sting.gatk.walkers.diagnostics.targets;
import org.broadinstitute.sting.commandline.Argument;
import org.broadinstitute.sting.commandline.Output;
import org.broadinstitute.sting.gatk.CommandLineGATK;
import org.broadinstitute.sting.gatk.contexts.AlignmentContext;
import org.broadinstitute.sting.gatk.contexts.ReferenceContext;
import org.broadinstitute.sting.gatk.refdata.RefMetaDataTracker;
@ -55,6 +56,8 @@ import org.broadinstitute.sting.gatk.report.GATKReport;
import org.broadinstitute.sting.gatk.walkers.LocusWalker;
import org.broadinstitute.sting.utils.GenomeLoc;
import org.broadinstitute.sting.utils.GenomeLocParser;
import org.broadinstitute.sting.utils.help.DocumentedGATKFeature;
import org.broadinstitute.sting.utils.help.HelpConstants;
import java.io.PrintStream;
import java.util.ArrayList;
@ -63,11 +66,11 @@ import java.util.LinkedList;
import java.util.Map;
/**
* Simple walker to plot the coverage distribution per base.
* Simple walker to plot the coverage distribution per base
*
* <p>
* Features of this walker:
* <li>includes a smart counting of uncovered bases without visiting the uncovered loci.</li>
* <li>includes a smart counting of uncovered bases without visiting the uncovered loci</li>
* <li>includes reads with deletions in the loci (optionally can be turned off)</li>
* </p>
*
@ -91,10 +94,11 @@ import java.util.Map;
* -fd \
* -o report.grp
* </pre>
* User: carneiro
* Date: 1/27/13
* Time: 11:16 AM
*
* @author carneiro
* @since 1/27/13
*/
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_QC, extraDocs = {CommandLineGATK.class} )
public class BaseCoverageDistribution extends LocusWalker<ArrayList<Integer>, Map<Integer, ArrayList<Long>>> {
/**
* The output GATK Report table

View File

@ -82,7 +82,7 @@ import java.util.*;
*
* This helper class holds the data HashMap as well as submaps that represent the marginal distributions collapsed over all needed dimensions.
* It also has static methods that are used to perform the various solid recalibration modes that attempt to correct the reference bias.
* This class holds the parsing methods that are shared between CountCovariates and TableRecalibration.
* This class holds the parsing methods that are shared between BaseRecalibrator and PrintReads.
*/
public class RecalUtils {

View File

@ -117,7 +117,7 @@ import java.util.*;
// todo -- alter logarithmic scaling to spread out bins more
// todo -- allow for user to set linear binning (default is logarithmic)
// todo -- formatting --> do something special for end bins in getQuantile(int[] foo), this gets mushed into the end+-1 bins for now
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_DATA, extraDocs = {CommandLineGATK.class} )
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_QC, extraDocs = {CommandLineGATK.class} )
@By(DataSource.REFERENCE)
@PartitionBy(PartitionType.NONE)
@Downsample(by= DownsampleType.NONE, toCoverage=Integer.MAX_VALUE)

View File

@ -29,12 +29,15 @@ package org.broadinstitute.sting.gatk.walkers.diagnostics;
import org.broadinstitute.sting.commandline.Argument;
import org.broadinstitute.sting.commandline.ArgumentCollection;
import org.broadinstitute.sting.commandline.Output;
import org.broadinstitute.sting.gatk.CommandLineGATK;
import org.broadinstitute.sting.gatk.arguments.StandardVariantContextInputArgumentCollection;
import org.broadinstitute.sting.gatk.contexts.AlignmentContext;
import org.broadinstitute.sting.gatk.contexts.ReferenceContext;
import org.broadinstitute.sting.gatk.refdata.RefMetaDataTracker;
import org.broadinstitute.sting.gatk.walkers.*;
import org.broadinstitute.sting.utils.GenomeLoc;
import org.broadinstitute.sting.utils.help.DocumentedGATKFeature;
import org.broadinstitute.sting.utils.help.HelpConstants;
import org.broadinstitute.variant.variantcontext.Genotype;
import org.broadinstitute.variant.variantcontext.GenotypesContext;
import org.broadinstitute.variant.variantcontext.VariantContext;
@ -44,12 +47,15 @@ import java.io.*;
import java.util.Collection;
/**
* print intervals file with all the variant sites that have "most" ( >= 90% by default) of the samples with "good" (>= 10 by default)coverage ("most" and "good" can be set in the command line).
* Print intervals file with all the variant sites for which most of the samples have good coverage
*
* <p>
* CoveredByNSamplesSites is a GATK tool for filter out sites based on their coverage.
* CoveredByNSamplesSites is a GATK tool for filtering out sites based on their coverage.
* The sites that pass the filter are printed out to an intervals file.
*
* See argument defaults for what constitutes "most" samples and "good" coverage. These parameters can be modified from the command line.
* </p>
*
* <h3>Input</h3>
* <p>
* A variant file and optionally min coverage and sample percentage values.
@ -60,7 +66,7 @@ import java.util.Collection;
* An intervals file.
* </p>
*
* <h3>Examples</h3>
* <h3>Example</h3>
* <pre>
* java -Xmx2g -jar GenomeAnalysisTK.jar \
* -R ref.fasta \
@ -71,7 +77,7 @@ import java.util.Collection;
* </pre>
*
*/
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_QC, extraDocs = {CommandLineGATK.class} )
@By(DataSource.REFERENCE_ORDERED_DATA)
public class CoveredByNSamplesSites extends RodWalker<GenomeLoc, Integer> implements TreeReducible<Integer> {

View File

@ -26,6 +26,7 @@
package org.broadinstitute.sting.gatk.walkers.variantutils;
import org.broadinstitute.sting.commandline.*;
import org.broadinstitute.sting.gatk.CommandLineGATK;
import org.broadinstitute.sting.gatk.contexts.AlignmentContext;
import org.broadinstitute.sting.gatk.contexts.ReferenceContext;
import org.broadinstitute.sting.gatk.refdata.RefMetaDataTracker;
@ -33,6 +34,8 @@ import org.broadinstitute.sting.gatk.report.GATKReport;
import org.broadinstitute.sting.gatk.report.GATKReportTable;
import org.broadinstitute.sting.gatk.walkers.RodWalker;
import org.broadinstitute.sting.utils.collections.Pair;
import org.broadinstitute.sting.utils.help.DocumentedGATKFeature;
import org.broadinstitute.sting.utils.help.HelpConstants;
import org.broadinstitute.sting.utils.variant.GATKVCFUtils;
import org.broadinstitute.variant.variantcontext.*;
import org.broadinstitute.variant.vcf.VCFHeader;
@ -41,29 +44,30 @@ import java.io.PrintStream;
import java.util.*;
/**
* A simple walker for performing genotype concordance calculations between two callsets. Outputs a GATK table with
* per-sample and aggregate counts and frequencies, a summary table for NRD/NRS, and a table for site allele overlaps.
* Genotype concordance (per-sample and aggregate counts and frequencies, NRD/NRS and site allele overlaps) between two callsets
*
* <p>
* Genotype concordance takes in two callsets (vcfs) and tabulates the number of sites which overlap and share alleles,
* GenotypeConcordance takes in two callsets (vcfs) and tabulates the number of sites which overlap and share alleles,
* and for each sample, the genotype-by-genotype counts (for instance, the number of sites at which a sample was
* called homozygous reference in the EVAL callset, but homozygous variant in the COMP callset). It outputs these
* counts as well as convenient proportions (such as the proportion of het calls in the EVAL which were called REF in
* the COMP) and metrics (such as NRD and NRS).
*
* <h2> INPUT </h2>
* <h3>Input</h3>
* <p>
* Genotype concordance requires two callsets (as it does a comparison): an EVAL and a COMP callset, specified via
* the -eval and -comp arguments
* <p>
* the -eval and -comp arguments.
*
* (Optional) Jexl expressions for genotype-level filtering of EVAL or COMP genotypes, specified via the -gfe and
* -cfe arguments, respectively.
* </p>
*
* <h2> OUTPUT </h2>
* Genotype Concordance writes a GATK report to the specified (via -o) file, consisting of multiple tables of counts
* <h3>Output</h3>
* Genotype Concordance writes a GATK report to the specified file (via -o) , consisting of multiple tables of counts
* and proportions. These tables may be optionally moltenized via the -moltenize argument.
*
*/
@DocumentedGATKFeature( groupName = HelpConstants.DOCS_CAT_VARMANIP, extraDocs = {CommandLineGATK.class} )
public class GenotypeConcordance extends RodWalker<List<Pair<VariantContext,VariantContext>>,ConcordanceMetrics> {
/**